Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Byrne
    -0.08
     Build
    -0.07
    уже
    -0.07
    _world
    -0.06
    ná
    -0.06
     resolver
    -0.06
    playlist
    -0.06
     Gravity
    -0.06
     hayata
    -0.06
     coz
    -0.06
    POSITIVE LOGITS
    oulouse
    0.07
    .iteritems
    0.06
    foods
    0.06
     grim
    0.06
    _CLOSE
    0.06
    .COL
    0.06
    Call
    0.06
     ￥
    0.06
     JSImport
    0.05
    thag
    0.05
    Act Density 0.247%

    No Known Activations